Model comparison
GLM-4.7-Flash vs Kimi K2 Thinking
- Input
- $0.06 / 1M tokens
- Output
- $0.40 / 1M tokens
- Context
- 200K
- Released
- 2026-01-19
- Input
- $0.60 / 1M tokens
- Output
- $2.50 / 1M tokens
- Context
- 256K
- Released
- 2025-11-06
Kimi K2 Thinking scores higher on 5 of the 5 benchmarks both models report; GLM-4.7-Flash is cheaper on input tokens ($0.1 vs $0.6 per 1M, 10×); Kimi K2 Thinking has the larger context window (256K vs 200K).
Specs and pricing side by side
| Spec | GLM-4.7-Flash | Kimi K2 Thinking |
|---|---|---|
| Maker | Z.ai (Zhipu / GLM) | Moonshot AI (Kimi) |
| Released | 2026-01-19 | 2025-11-06 |
| Context window | 200K | 256K |
| Max output | 128K | 256K |
| Input price | $0.06 / 1M tokens | $0.60 / 1M tokens |
| Output price | $0.40 / 1M tokens | $2.50 / 1M tokens |
| Parameters | 30B total / 3B active (30B-A3B MoE) | 1T total / 32B active (MoE) |
| License | MIT | Modified MIT License |
| Weights | Open weights | Open weightssame |
| Modalities | Text | Textsame |
Not published by either maker: knowledge cutoff.
Benchmarks both models report
| Benchmark | GLM-4.7-Flash | Kimi K2 Thinking |
|---|---|---|
| GPQA | 75.2% | 84.5% |
| LiveCodeBench v6 | 64% | 83.1% |
| SWE-bench Verified | 59.2% | 71.3% |
| BrowseComp | 42.8% | 60.2% |
| Humanity's Last Exam | 14.4% | 44.9% |
Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.
Which one should you pick?
Pick GLM-4.7-Flash if…
- Cost matters: input tokens cost 10× less ($0.1 vs $0.6 per 1M).
- Your use case is: local and self-hosted AI coding assistants on a single GPU or capable workstation.
Pick Kimi K2 Thinking if…
- You care about GPQA, LiveCodeBench v6, SWE-bench Verified (it scores higher on 5 shared benchmarks).
- You need the longer context (256K vs 200K).
- Your use case is: autonomous research agents that browse, gather, and synthesize across many steps.
FAQ
Which is better, GLM-4.7-Flash or Kimi K2 Thinking?
Kimi K2 Thinking scores higher on 5 of the 5 benchmarks both models report; GLM-4.7-Flash is cheaper on input tokens ($0.1 vs $0.6 per 1M, 10×); Kimi K2 Thinking has the larger context window (256K vs 200K). The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How much cheaper is GLM-4.7-Flash?
GLM-4.7-Flash: $0.06 / 1M tokens input, $0.40 / 1M tokens output. Kimi K2 Thinking: $0.60 / 1M tokens input, $2.50 / 1M tokens output (list API prices as published by each maker).
What are the context windows of GLM-4.7-Flash and Kimi K2 Thinking?
GLM-4.7-Flash offers 200K with up to 128K output; Kimi K2 Thinking offers 256K with up to 256K output.
Is GLM-4.7-Flash newer than Kimi K2 Thinking?
GLM-4.7-Flash was released 2026-01-19; Kimi K2 Thinking was released 2025-11-06.
Go deeper
- GLM-4.7-Flash: full specs, pricing and benchmarks
- Kimi K2 Thinking: full specs, pricing and benchmarks
- kimi k2 thinking vs deepseek v3 1
- kimi k2 thinking vs deepseek v3 2 exp
- glm 5 3 flash vs glm 4 7 flash
- glm 4 7 flash vs minimax m2
- kimi k2 thinking vs deepseek v3 1 terminus
- glm 4 7 flash vs gemini 3 flash
- All model comparisons